gen_ai.request.max_tokens
MovedGenAI registryintas of v1.44.0
The maximum number of tokens the model generates for a request.
Examples
- 100
Used by
events (1)
- gen_ai.client.inference.operation.details
spans (7)
- span.anthropic.inference.client
- span.aws.bedrock.client
- span.azure.ai.inference.client
- span.gen_ai.inference.client
- span.gen_ai.invoke_agent.client
- span.gen_ai.invoke_agent.internal
- span.openai.inference.client
* required on that signal.
History
- v1.42.0deprecated
Moved to the OpenTelemetry GenAI semantic conventions repository.
Stability label respelled from experimental to development.
Already present at v1.30.0, the oldest release tracked here (experimental).